Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Löwe, Sindy"'
It has long been known in both neuroscience and AI that ``binding'' between neurons leads to a form of competitive learning where representations are compressed in order to represent more abstract concepts in deeper layers of the network. More recent
Externí odkaz:
http://arxiv.org/abs/2410.13821
In human cognition, the binding problem describes the open question of how the brain flexibly integrates diverse information into cohesive object representations. Analogously, in machine learning, there is a pursuit for models capable of strong gener
Externí odkaz:
http://arxiv.org/abs/2402.05627
Autor:
Lippe, Phillip, Magliacane, Sara, Löwe, Sindy, Asano, Yuki M., Cohen, Taco, Gavves, Efstratios
Identifying the causal variables of an environment and how to intervene on them is of core value in applications such as robotics and embodied AI. While an agent can commonly interact with the environment and may implicitly perturb the behavior of so
Externí odkaz:
http://arxiv.org/abs/2306.09643
The binding problem in human cognition, concerning how the brain represents and connects objects within a fixed network of neural connections, remains a subject of intense debate. Most machine learning efforts addressing this issue in an unsupervised
Externí odkaz:
http://arxiv.org/abs/2306.00600
Autor:
Lippe, Phillip, Magliacane, Sara, Löwe, Sindy, Asano, Yuki M., Cohen, Taco, Gavves, Efstratios
Causal representation learning is the task of identifying the underlying causal variables and their relations from high-dimensional observations, such as images. Recent work has shown that one can reconstruct the causal variables from temporal sequen
Externí odkaz:
http://arxiv.org/abs/2206.06169
Object-centric representations form the basis of human perception, and enable us to reason about the world and to systematically generalize to new settings. Currently, most works on unsupervised object discovery focus on slot-based approaches, which
Externí odkaz:
http://arxiv.org/abs/2204.02075
Autor:
Lippe, Phillip, Magliacane, Sara, Löwe, Sindy, Asano, Yuki M., Cohen, Taco, Gavves, Efstratios
Understanding the latent causal factors of a dynamical system from visual observations is considered a crucial step towards agents reasoning in complex environments. In this paper, we propose CITRIS, a variational autoencoder framework that learns ca
Externí odkaz:
http://arxiv.org/abs/2202.03169
Autor:
de Haan, Puck, Löwe, Sindy
Reliable detection of anomalies is crucial when deploying machine learning models in practice, but remains challenging due to the lack of labeled data. To tackle this challenge, contrastive learning approaches are becoming increasingly popular, given
Externí odkaz:
http://arxiv.org/abs/2107.07820
Contrastive, self-supervised learning of object representations recently emerged as an attractive alternative to reconstruction-based training. Prior approaches focus on contrasting individual object representations (slots) against one another. Howev
Externí odkaz:
http://arxiv.org/abs/2011.10287
On time-series data, most causal discovery methods fit a new model whenever they encounter samples from a new underlying causal graph. However, these samples often share relevant information which is lost when following this approach. Specifically, d
Externí odkaz:
http://arxiv.org/abs/2006.10833